get_screenshot_at_failure

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the output format (base64 JPEG) and the selection behavior (nearest to failure or specific index). However, it does not mention edge cases like missing screenshots or invalid indices, which prevents a perfect score.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is only two sentences long, front-loaded with the core purpose, and every clause earns its place—purpose, usage trigger, and parameter behavior are all covered without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple retrieval tool with no output schema, the description sufficiently explains the return format (base64 JPEG) and the two modes of use. It could add error-handling notes (e.g., what happens if no screenshot exists), but overall it provides enough context for an agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are already described in the input schema, including the 0-based indexing and the omit-to-get-failure behavior. The description essentially repeats this information without adding meaningful new semantics, so it stays at the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Returns' and the resource 'screenshot (base64 JPEG) from the trace', with specific scope 'closest to the moment of failure'. It also distinguishes from siblings by explicitly referencing get_aria_accessibility_tree as an alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives an explicit when-to-use condition: 'Use when get_aria_accessibility_tree returns an empty or unhelpful tree'. It also explains the choice between default (nearest to failure) and passing screenshot_index, providing clear decision guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.